From a4c5ecfb1bc0101c1b42a4d81bb427482b52cecf Mon Sep 17 00:00:00 2001
From: Benjamin Kramer <benny.kra@googlemail.com>
Date: Sat, 3 Mar 2012 19:13:26 +0000
Subject: [PATCH] Shrink the asm matcher tables.

- Shrink the opcode field to 16 bits.
- Shrink the AsmVariantID field to 8 bits.
- Store the mnemonic string in a string table, store a 16 bit index.
- Store a pascal-style length byte in the string instead of a null terminator,
  so we can avoid calling strlen on every entry we visit during mnemonic search.

Shrinks X86AsmParser.o from 434k to 201k on x86_64 and eliminates relocs from the table.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151984 91177308-0d34-0410-b5e6-96231b3b80d8
---
 utils/TableGen/AsmMatcherEmitter.cpp | 31 +++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 8 deletions(-)

diff --git a/utils/TableGen/AsmMatcherEmitter.cpp b/utils/TableGen/AsmMatcherEmitter.cpp
index 80467ff3dc7..7b438842418 100644
--- a/utils/TableGen/AsmMatcherEmitter.cpp
+++ b/utils/TableGen/AsmMatcherEmitter.cpp
@@ -99,6 +99,7 @@
 #include "AsmMatcherEmitter.h"
 #include "CodeGenTarget.h"
 #include "StringMatcher.h"
+#include "StringToOffsetTable.h"
 #include "llvm/ADT/OwningPtr.h"
 #include "llvm/ADT/PointerUnion.h"
 #include "llvm/ADT/SmallPtrSet.h"
@@ -2302,32 +2303,39 @@ void AsmMatcherEmitter::run(raw_ostream &OS) {
   // following the mnemonic.
   OS << "namespace {\n";
   OS << "  struct MatchEntry {\n";
-  OS << "    unsigned Opcode;\n";
-  OS << "    const char *Mnemonic;\n";
+  OS << "    static const char *MnemonicTable;\n";
+  OS << "    uint16_t Opcode;\n";
+  OS << "    uint16_t Mnemonic;\n";
   OS << "    " << getMinimalTypeForRange(Info.Matchables.size())
                << " ConvertFn;\n";
   OS << "    " << getMinimalTypeForRange(Info.Classes.size())
                << " Classes[" << MaxNumOperands << "];\n";
   OS << "    " << getMinimalTypeForRange(1ULL << Info.SubtargetFeatures.size())
                << " RequiredFeatures;\n";
-  OS << "    unsigned AsmVariantID;\n";
+  OS << "    uint8_t AsmVariantID;\n\n";
+  OS << "    StringRef getMnemonic() const {\n";
+  OS << "      return StringRef(MnemonicTable + Mnemonic + 1,\n";
+  OS << "                       MnemonicTable[Mnemonic]);\n";
+  OS << "    }\n";
   OS << "  };\n\n";
 
   OS << "  // Predicate for searching for an opcode.\n";
   OS << "  struct LessOpcode {\n";
   OS << "    bool operator()(const MatchEntry &LHS, StringRef RHS) {\n";
-  OS << "      return StringRef(LHS.Mnemonic) < RHS;\n";
+  OS << "      return LHS.getMnemonic() < RHS;\n";
   OS << "    }\n";
   OS << "    bool operator()(StringRef LHS, const MatchEntry &RHS) {\n";
-  OS << "      return LHS < StringRef(RHS.Mnemonic);\n";
+  OS << "      return LHS < RHS.getMnemonic();\n";
   OS << "    }\n";
   OS << "    bool operator()(const MatchEntry &LHS, const MatchEntry &RHS) {\n";
-  OS << "      return StringRef(LHS.Mnemonic) < StringRef(RHS.Mnemonic);\n";
+  OS << "      return LHS.getMnemonic() < RHS.getMnemonic();\n";
   OS << "    }\n";
   OS << "  };\n";
 
   OS << "} // end anonymous namespace.\n\n";
 
+  StringToOffsetTable StringTable;
+
   OS << "static const MatchEntry MatchTable["
      << Info.Matchables.size() << "] = {\n";
 
@@ -2336,8 +2344,11 @@ void AsmMatcherEmitter::run(raw_ostream &OS) {
        it != ie; ++it) {
     MatchableInfo &II = **it;
 
+    // Store a pascal-style length byte in the mnemonic.
+    std::string LenMnemonic = char(II.Mnemonic.size()) + II.Mnemonic.str();
     OS << "  { " << Target.getName() << "::"
-       << II.getResultInst()->TheDef->getName() << ", \"" << II.Mnemonic << "\""
+       << II.getResultInst()->TheDef->getName() << ", "
+       << StringTable.GetOrAddStringOffset(LenMnemonic, false)
        << ", " << II.ConversionFnKind << ", { ";
     for (unsigned i = 0, e = II.AsmOperands.size(); i != e; ++i) {
       MatchableInfo::AsmOperand &Op = II.AsmOperands[i];
@@ -2361,6 +2372,10 @@ void AsmMatcherEmitter::run(raw_ostream &OS) {
 
   OS << "};\n\n";
 
+  OS << "const char *MatchEntry::MnemonicTable =\n";
+  StringTable.EmitString(OS);
+  OS << ";\n\n";
+
   // A method to determine if a mnemonic is in the list.
   OS << "bool " << Target.getName() << ClassName << "::\n"
      << "MnemonicIsValid(StringRef Mnemonic) {\n";
@@ -2424,7 +2439,7 @@ void AsmMatcherEmitter::run(raw_ostream &OS) {
   OS << "       it != ie; ++it) {\n";
 
   OS << "    // equal_range guarantees that instruction mnemonic matches.\n";
-  OS << "    assert(Mnemonic == it->Mnemonic);\n";
+  OS << "    assert(Mnemonic == it->getMnemonic());\n";
 
   // Emit check that the subclasses match.
   OS << "    if (VariantID != it->AsmVariantID) continue;\n";